@mitchellh If you'd have told me 2 years ago that you'd be able to give an agent a goal like this, have it come up with candidate changes, write functional Go, and make substantial improvements, I'd have thought it was pretty incredible.
Interesting how quickly expectations are shifting
@iannuttall 5.4 high in Codex did something interesting yesterday. It started delegating changes to subagents using 5.4-mini.
Context was being forked. It was also observing the changes for issues. It did use 5.4 high for a more complex change later on.
Impressed
Introducing Seclai!
We built the AI agent platform we always needed as engineers.
No more boilerplate. No more plumbing.
No more blind spots in production.
Just build, deploy, and ship AI agents in minutes.
Check it out here: https://t.co/mWhGvm253i
@julietremaine@DisneyParks@Disneyland we feel your pain! Having been on both sides of drops @rival, we built https://t.co/J9DKUIxkEf to smooth things out. Here if you need us!
System failures this summer have resulted in unhappy Disneyland fans who can’t get tickets to upcoming events, and on some days, are unable to get into the theme park itself. https://t.co/aYOSDeQA4E
I love that @cyantist spoke about her background. I never knew any of this. Remarkable. I only knew her as the self-confident, curious, capable, friendly co-board member at @densityio. Never assume you know anybody's journey. You'll enjoy this https://t.co/u5W8JTA8sM
Wow! Totally blown away by the maturity of the serverless CI/CD pipeline that @rival built! So cool. Would love to have you all on https://t.co/MFblbeRfVh with @nicki_23 and @mkosut !
Let's talk about influence. As an engineer, how do you get it, earn it, wield it, or lose it?
(The answer is NOT "become a manager.". In a well-functioning org, managers have mostly separate sphere of influence. If this is not true of yours, change it or leave.)
Thread.
Thread.
I was recently privy to a conversation in which some really smart people in security shared their favorite papers or articles. Security engineering, like other disciplines, has a rich history worth learning from.
I'm going to list some of these papers in this thread.